Figure 2 Selection of laboratory parameters by the least absolute shrinkage and selection operator (LASSO) binary logistic regression model. (A) The optimal parameter was selected based on fivefold cross-validation in the LASSO model. (B) LASSO coefficient profiles of the nine features. A coefficient profile plot was produced against the log (lambda) sequence. Fivefold cross-validation was used to draw a vertical line at the selected value, where optimal lambda identified five variables with non-zero coefficients. LASSO, least absolute shrinkage, and selection operator.